1 title: //h1[@class='page-heading']
2 author: //small/strong/a
3 #their date string is relative, so if you save the page 2 hours after it is posted it may say 'two hours ago, instead of providing a useful date/time'
4 date: substring-before(substring-after(//small,'on'),'with')
5 body: //div[@class='entry']
6 test_url: http://www.winrumors.com/chinese-windows-phone-launch-still-on-track-for-early-2012/